Converge Blog Predicting concrete performance with sensor data and AI

The last 12 months have seen exciting developments emerge at Converge. Using funding from an Innovate UK grant awarded in late 2018, Converge has collaborated with BAM Nuttall to develop the first commercial machine learning programme for concrete. This sort of innovation is hugely impactful for the construction industry.Despite being one of the biggest industries in the world, contributing 10–15% of world GDP, construction is the second least digitised of them all. Converge has been a front-runner in bringing construction into the digital age, by developing wireless and cloud-based technology that provides neat solutions to project management problems faced by our clients. Our mission is to build the future more efficiently, safely, and sustainably by digitising physical reality on the jobsite.In the 5 years since our inception, Converge has enabled leading construction companies to drive efficiencies by shortening concrete cycles with real-time strength data generated from sensors embedded onsite. This digital revolution has taken concrete monitoring from something of an art, which relied heavily on human judgement (and error), into a process more akin to an exact science.We are now taking one (giant) step further, with the world’s first artificial intelligence (AI) concrete strength prediction engine, through which Converge can provide powerful and sophisticated predictive power to our customers. By enabling greater insight into the performance of materials, we are enabling jobsites to make huge gains in terms of productivity, efficiency, and sustainability. This advancement is enormously exciting.We are already seeing the potential of this innovation come to fruition: the strength prediction engine is currently being utilised on BAM Nuttall’s London City Airport expansion project, where we are verifying the significant scope of this technology to keep projects on track and maximise efficiency. We are excited to roll out this advancement in construction technology to jobsites worldwide.The key benefit of the prediction engine is that it allows project managers to schedule tasks much further in advance than ever before, thus allowing them to save time and stay on schedule. Whilst the alerts and live data generated by the original Converge system bring significant project management benefits, an extensive customer survey revealed that resultant actions often were not being taken until many hours after critical strengths were reached. Ultimately, this was because users were waiting for concrete to hit a critical strength before scheduling the next activity. When the time came to act, however, the site teams needed to strike formwork or tension the slab were often deployed in other areas, leading to delays.While such delays are small, when accumulated across hundreds of cycles they result in weeks of lost potential progress. When concrete sits on the critical path, the costs associated with these time lags costs the industry millions of pounds every year. To combat this inefficiency, Converge used the Innovate UK grant, together with BAM Nuttall, to develop the industry’s first and most advanced AI strength prediction engine. The BAM Nuttall team, led by Colin Evison, have been ideal collaborators over the past four years. Converge and BAM share a common vision about the future of construction, which is why we were enthused about tackling this Innovate UK grant project in partnership with them.The predictions engine was made possible by Converge’s unique access to a huge concrete performance data set, paving the way for the first commercial application of Machine Learning to monitor and predict material performance. Within hours of concrete being poured, Converge can predict the time a critical strength will be reached, several days in advance. To achieve this, the predictions engine combines local weather data, a database of historical concrete curing data, and the Converge concrete monitoring platform’s real-time measurements from the pour. This gives Converge the unique ability to predict the time the concrete will reach strength with an accuracy of +/- 5%, days in advance.The result of this immense predictive power is that project teams can plan to take action precisely when needed. This improved workflow allows projects to increase productivity and stay on track, which can ultimately save millions of pounds. We are enabling the industry to build the future more efficiently, safely, and sustainably.Of course, for Converge, concrete is only the beginning; when sensors are embedded not only in concrete slabs, but a variety of other structural elements, and when that data is combined to form a complete picture of what is happening onsite, the possibilities for optimisation become countless. That is something we are incredibly excited about. This is the first of many cutting-edge capabilities that the Innovation UK grant has allowed Converge to deliver, so watch this space!If you are interested in seeing how we can help your project or organisation using our sensors and AI, just get in touch at hello@converge.io.Predicting concrete performance with sensor data and AI was originally published in Converge on Medium, where people are continuing the conversation by highlighting and responding to this story.